© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7637
    Prev
    Next
    INDEX
    Explanations

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭ©
    -0.09
    ICO
    -0.09
     Firm
    -0.07
    æĪijä¸Ģ缴
    -0.07
    YRO
    -0.07
    cheon
    -0.07
     Desmond
    -0.07
    çĴł
    -0.07
    æ¯ħåĬĽ
    -0.07
    dehy
    -0.07
    POSITIVE LOGITS
    sep
    0.12
    羯
    0.11
    -Ta
    0.10
     lag
    0.10
    æĶ¾å¿ĥ
    0.09
    ä¸Ģéĥ¨åĪĨ
    0.09
    æ±IJ
    0.09
    cade
    0.09
    ardo
    0.09
    ook
    0.08
    Activations Density 0.142%

    No Known Activations